James McDermott jmmcd
-
National University of Ireland, Galway
- Galway, Ireland
- http://jmmcd.net
jmmcd
/ pg-pong.py
Last active Dec 1, 2016
— forked from karpathy/pg-pong.py
Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels
View pg-pong.py
| """from | |
| https://gist.github.com/karpathy/a4166c7fe253700972fcbc77e4ea32c5 | |
| http://karpathy.github.io/2016/05/31/rl/ | |
| I've converted to Python 3, added command-line args, added slightly | |
| more informative episode status message, allowed reloading of running | |
| reward, episode number, and elapsed time, and switched off the | |
| per-point status message -- jmmcd. |
jmmcd
/ fit_const_lr_enet.py
Last active Dec 30, 2015
Snippet for reading in a table of numbers and predicting the last column as a function of the others, using either just a constant, or linear regression, or linear regression regularised with the elastic net. Uses Numpy and Scikit-learn.
View fit_const_lr_enet.py
| #!/usr/bin/env python | |
| from __future__ import print_function | |
| import numpy as np | |
| from sklearn.linear_model import ElasticNet, LinearRegression | |
| import sys | |
| # James McDermott (c) 2013 | |
| # Hosted at https://gist.github.com/jmmcd/7790588 | |
| # Requires Numpy and Scikit-learn |